Fushuo Huo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Fushuo Huo has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Song Guo
Hong Kong University of Science and Technology, Hong Kong, China
5 shared publications - Wenchao Xu
The Hong Kong University of Science and Technology, Hong Kong Sar, China
4 shared publications - Ziming Liu
Department of Computing The Hong Kong Polytechnic University Hong Kong SAR China
4 shared publications - Jingcai Guo
The Hong Kong Polytechnic University, Hong Kong SAR, China
3 shared publications - Xuegui Zhu
State Key Laboratory of Power Transmission Equipment Technology, School of Electrical Engineering, Chongqing University, Chongqing 400044, China
3 shared publications Bingheng Li
2 shared publications
Latest Publications
- 12 September 2026
- Published by Springer Nature
- p. 133-150
One Trap to Block Them All: Defending Encoder Stealing via Isotropic Uniformity
- 12 September 2026
- Published by Springer Nature
- p. 133-150
One Trap to Block Them All: Defending Encoder Stealing via Isotropic Uniformity
- 18 June 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 331
GLGaze: In-vehicle gaze estimation via joint global-local enhancement in the spatial and scale domains
- 18 June 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 331
GLGaze: In-vehicle gaze estimation via joint global-local enhancement in the spatial and scale domains
- 1 November 2024
- Published by Springer Nature
- p. 178-195
Overcome Modal Bias in Multi-modal Federated Learning via Balanced Modality Selection
- 1 November 2024
- Published by Springer Nature
- p. 178-195
Overcome Modal Bias in Multi-modal Federated Learning via Balanced Modality Selection
- 3 January 2024
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 98
REQA: Coarse-to-fine assessment of image quality to alleviate the range effect
- 3 January 2024
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 98
REQA: Coarse-to-fine assessment of image quality to alleviate the range effect
- 24 November 2023
- Published by Elsevier in Neural Networks
- Vol. 170, 521-534
UTDNet: A unified triplet decoder network for multimodal salient object detection
- 24 November 2023
- Published by Elsevier in Neural Networks
- Vol. 170, 521-534
UTDNet: A unified triplet decoder network for multimodal salient object detection
- Open Access
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (6) , 7775-7783
Graph Knows Unknowns: Reformulate Zero-Shot Learning as Sample-Level Graph Recognition
Zero-shot learning (ZSL) is an extreme case of transfer learning that aims to recognize samples (e.g., images) of unseen classes relying on a train-set covering only seen classes and a set of auxiliary knowledge (e.g., semantic descriptors). Existing methods usually resort to constructing a visual-to-semantics mapping based on features extracted from each whole sample. However, since the visual and semantic spaces are inherently independent and may exist in different manifolds, these methods may easily suffer from the domain bias problem due to the knowledge transfer from seen to unseen classes. Unlike existing works, this paper investigates the fine-grained ZSL from a novel perspective of sample-level graph. Specifically, we decompose an input into several fine-grained elements and construct a graph structure per sample to measure and utilize element-granularity relations within each sample. Taking advantage of recently developed graph neural networks (GNNs), we formulate the ZSL problem to a graph-to-semantics mapping task, which can better exploit element-semantics correlation and local sub-structural information in samples. Experimental results on the widely used benchmark datasets demonstrate that the proposed method can mitigate the domain bias problem and achieve competitive performance against other representative methods.
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (6) , 7775-7783
Open AccessGraph Knows Unknowns: Reformulate Zero-Shot Learning as Sample-Level Graph Recognition
Zero-shot learning (ZSL) is an extreme case of transfer learning that aims to recognize samples (e.g., images) of unseen classes relying on a train-set covering only seen classes and a set of auxiliary knowledge (e.g., semantic descriptors). Existing methods usually resort to constructing a visual-to-semantics mapping based on features extracted from each whole sample. However, since the visual and semantic spaces are inherently independent and may exist in different manifolds, these methods may easily suffer from the domain bias problem due to the knowledge transfer from seen to unseen classes. Unlike existing works, this paper investigates the fine-grained ZSL from a novel perspective of sample-level graph. Specifically, we decompose an input into several fine-grained elements and construct a graph structure per sample to measure and utilize element-granularity relations within each sample. Taking advantage of recently developed graph neural networks (GNNs), we formulate the ZSL problem to a graph-to-semantics mapping task, which can better exploit element-semantics correlation and local sub-structural information in samples. Experimental results on the widely used benchmark datasets demonstrate that the proposed method can mitigate the domain bias problem and achieve competitive performance against other representative methods.
- Open Access
DRPT: Disentangled and Recurrent Prompt Tuning for Compositional Zero-Shot Learning
Compositional Zero-shot Learning (CZSL) aims to recognize novel concepts composed of known knowledge without training samples. Standard CZSL either identifies visual primitives or enhances unseen composed entities, and as a result, entanglement between state and object primitives cannot be fully utilized. Admittedly, vision-language models (VLMs) could naturally cope with CZSL through tuning prompts, while uneven entanglement leads prompts to be dragged into local optimum. In this paper, we take a further step to introduce a novel Disentangled and Recurrent Prompt Tuning framework termed DRPT to better tap the potential of VLMs in CZSL. Specifically, the state and object primitives are deemed as learnable tokens of vocabulary embedded in prompts and tuned on seen compositions. Instead of jointly tuning state and object, we devise a disentangled and recurrent tuning strategy to suppress the traction force caused by entanglement and gradually optimize the token parameters, leading to a better prompt space. Notably, we develop a progressive fine-tuning procedure that allows for incremental updates to the prompts, optimizing the object first, then the state, and vice versa. Meanwhile, the optimization of state and object is independent, thus clearer features can be learned to further alleviate the issue of entangling misleading optimization. Moreover, we quantify and analyze the entanglement in CZSL and supplement entanglement rebalancing optimization schemes. DRPT surpasses representative state-of-the-art methods on extensive benchmark datasets, demonstrating superiority in both accuracy and efficiency.
Open AccessDRPT: Disentangled and Recurrent Prompt Tuning for Compositional Zero-Shot Learning
Compositional Zero-shot Learning (CZSL) aims to recognize novel concepts composed of known knowledge without training samples. Standard CZSL either identifies visual primitives or enhances unseen composed entities, and as a result, entanglement between state and object primitives cannot be fully utilized. Admittedly, vision-language models (VLMs) could naturally cope with CZSL through tuning prompts, while uneven entanglement leads prompts to be dragged into local optimum. In this paper, we take a further step to introduce a novel Disentangled and Recurrent Prompt Tuning framework termed DRPT to better tap the potential of VLMs in CZSL. Specifically, the state and object primitives are deemed as learnable tokens of vocabulary embedded in prompts and tuned on seen compositions. Instead of jointly tuning state and object, we devise a disentangled and recurrent tuning strategy to suppress the traction force caused by entanglement and gradually optimize the token parameters, leading to a better prompt space. Notably, we develop a progressive fine-tuning procedure that allows for incremental updates to the prompts, optimizing the object first, then the state, and vice versa. Meanwhile, the optimization of state and object is independent, thus clearer features can be learned to further alleviate the issue of entangling misleading optimization. Moreover, we quantify and analyze the entanglement in CZSL and supplement entanglement rebalancing optimization schemes. DRPT surpasses representative state-of-the-art methods on extensive benchmark datasets, demonstrating superiority in both accuracy and efficiency.
- 16 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 7441-7455
Towards Unbiased Multi-Label Zero-Shot Learning With Pyramid and Semantic Attention
Multi-label zero-shot learning extends conventional single-label zero-shot learning to a more realistic scenario that aims at recognizing multiple unseen labels of classes for each input sample. Existing works usually exploit attention mechanism to generate the correlation among different labels. However, most of them are usually biased on several major classes while neglect most of the minor classes with the same importance in input samples, and may thus result in overly diffused attention maps that cannot sufficiently cover minor classes . We argue that disregarding the connection between major and minor classes, i.e., correspond to the global and local information, respectively, is the cause of the problem. In this paper, we propose a novel framework of unbiased multi-label zero-shot learning, by considering various class-specific regions to calibrate the training process of the classifier. Specifically, Pyramid Feature Attention ( PFA ) is proposed to build the correlation between global and local information of samples to balance the presence of each class. Meanwhile, for the generated semantic representations of input samples, we propose Semantic Attention ( SA ) to strengthen the element-wise correlation among these vectors, which can encourage the coordinated representation of them. Extensive experiments on the large-scale multi-label benchmarks MS-COCO , NUS-WIDE and Open-Images demonstrate that the proposed method surpasses other representative methods by significant margins.
- 16 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 7441-7455
Towards Unbiased Multi-Label Zero-Shot Learning With Pyramid and Semantic Attention
Multi-label zero-shot learning extends conventional single-label zero-shot learning to a more realistic scenario that aims at recognizing multiple unseen labels of classes for each input sample. Existing works usually exploit attention mechanism to generate the correlation among different labels. However, most of them are usually biased on several major classes while neglect most of the minor classes with the same importance in input samples, and may thus result in overly diffused attention maps that cannot sufficiently cover minor classes . We argue that disregarding the connection between major and minor classes, i.e., correspond to the global and local information, respectively, is the cause of the problem. In this paper, we propose a novel framework of unbiased multi-label zero-shot learning, by considering various class-specific regions to calibrate the training process of the classifier. Specifically, Pyramid Feature Attention ( PFA ) is proposed to build the correlation between global and local information of samples to balance the presence of each class. Meanwhile, for the generated semantic representations of input samples, we propose Semantic Attention ( SA ) to strengthen the element-wise correlation among these vectors, which can encourage the coordinated representation of them. Extensive experiments on the large-scale multi-label benchmarks MS-COCO , NUS-WIDE and Open-Images demonstrate that the proposed method surpasses other representative methods by significant margins.